Ren-Wei/Safe-RLHF-DPO-naive-baseline-epoch4-llama3-8b
Updated • 2
Liang
Ren-Wei
AI & ML interests
None yet
Organizations
None yet
Ren-Wei/Safe-RLHF-DPO-naive-baseline-llama3-8b
Updated • 3
Ren-Wei/Safe-RLHF-DPO-helpful-llama3-8b
Updated • 2
Ren-Wei/Safe-RLHF-DPO-helpless-llama3-8b
Updated • 1
Ren-Wei/Safe-RLHF-DPO-harmless-llama3-8b
Updated • 2
Ren-Wei/Safe-RLHF-DPO-harmful-llama3-8b
Updated • 1
Ren-Wei/Safe-RLHF-DPO-naive-baseline-epoch4-llama3-3b
Updated • 1
Ren-Wei/Safe-RLHF-DPO-naive-baseline-llama3-3b
Updated • 1
Ren-Wei/Safe-RLHF-DPO-helpful-llama3-3b
Updated • 3
Ren-Wei/Safe-RLHF-DPO-helpless-llama3-3b
Updated • 1
Ren-Wei/Safe-RLHF-DPO-harmless-llama3-3b
Updated • 1
Ren-Wei/Safe-RLHF-DPO-harmful-llama3-3b
Updated • 1
Ren-Wei/Safe-RLHF-SFT-llama3-3b
Updated • 1
Ren-Wei/Safe-RLHF-SFT-mistral-7b
Updated • 1
Ren-Wei/Safe-RLHF-PPO-Lag-baseline-opt-1b
1B • Updated • 3
Ren-Wei/Safe-RLHF-DPO-naive-baseline-opt-3b
3B • Updated • 1
Ren-Wei/Safe-RLHF-DPO-naive-baseline-opt-1b
1B • Updated • 1
Ren-Wei/Safe-RLHF-PPO-helpless-opt-1b
1B • Updated • 2
Ren-Wei/Safe-RLHF-PPO-harmless-opt-1b
1B • Updated • 2
Ren-Wei/Safe-RLHF-DPO-helpless-opt-3b
3B • Updated • 3
Ren-Wei/Safe-RLHF-DPO-helpful-opt-3b
3B • Updated • 2
Ren-Wei/Safe-RLHF-DPO-harmless-opt-3b
3B • Updated • 2
Ren-Wei/Safe-RLHF-DPO-harmful-opt-3b
3B • Updated • 3
Ren-Wei/Safe-RLHF-SFT-opt-3b
3B • Updated • 5
Ren-Wei/Safe-RLHF-DPO-harmful-opt-1b
1B • Updated • 3
Ren-Wei/Safe-RLHF-DPO-helpless-opt-1b
1B • Updated • 2
Ren-Wei/Safe-RLHF-DPO-helpful-opt-1b
1B • Updated • 2
Ren-Wei/Safe-RLHF-DPO-harmless-opt-1b
1B • Updated • 3
Ren-Wei/Safe-RLHF-SFT-opt-1b
1B • Updated • 1
Ren-Wei/Safe-RLHF-PPO-helpful-opt-1b
1B • Updated • 1